Coupled neural associative memories

We propose a novel architecture to design a neural associative memory that is capable of learning a large number of patterns and recalling them later in presence of noise. It is based on dividing the neurons into local clusters and parallel plains, an architecture that is similar to the visual cortex of macaque brain. The common features of our proposed model with those of spatially-coupled codes enable us to show that the performance of such networks in eliminating noise is drastically better than the previous approaches while maintaining the ability of learning an exponentially large number of patterns. Previous work either failed in providing good performance during the recall phase or in offering large pattern retrieval (storage) capacities. We also present computational experiments that lend additional support to the theoretical analysis.


Published in:
Proc. IEEE Information Theory Workshop (ITW), 1 - 5
Presented at:
IEEE Information Theory Workshop (ITW), Seville, Spain, September 9-13, 2013
Year:
2013
Publisher:
IEEE
ISBN:
10.1109/ITW.2013.6691267
Keywords:
Note:
The code for the simulations performed in this paper is available at the following link: https://github.com/saloot/NeuralAssociativeMemory/tree/master/Codes%20Used%20in%20Papers/Coupled%20neural%20associative%20memories%20(ITW%202013)
Laboratories:




 Record created 2014-06-10, last modified 2018-09-13

Preprint:
Download fulltextPDF
Presentation for the paper:
Download fulltextPDF
The extended version of te paper:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)